© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23277
    Prev
    Next
    INDEX
    Explanations

    served or serving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºİæѤ
    -0.10
    ä¸įä¿¡
    -0.10
    ÑıÑģ
    -0.09
    æĿ¥çĶµ
    -0.09
    æ¡ĥ
    -0.09
    æīĵäºĨ
    -0.09
     Downloads
    -0.09
    éĻį
    -0.09
    _sq
    -0.09
    åħĨ
    -0.09
    POSITIVE LOGITS
    thin
    0.09
    æľįåĬ¡æ°´å¹³
    0.09
    æľįåĬ¡
    0.09
    伪
    0.09
     service
    0.09
    æµij
    0.09
    punk
    0.09
    伶
    0.09
    端
    0.08
    åĴĮæľįåĬ¡
    0.08
    Activations Density 0.055%

    No Known Activations